Repository Public
1---2title: Archive Session Thread3url: https://platform.claude.com/docs/en/api/beta/sessions/threads/archive4---56# Archive Session Thread78**POST** `/v1/sessions/{session_id}/threads/{thread_id}/archive`910Archive Session Thread1112## Path parameters1314- `session_id: string`1516- `thread_id: string`1718## Headers1920- `"anthropic-beta": optional array of AnthropicBeta`2122 Optional header to specify the beta version(s) you want to use.2324 - `string`2526 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 43 more`2728 - `"message-batches-2024-09-24"`2930 - `"prompt-caching-2024-07-31"`3132 - `"computer-use-2024-10-22"`3334 - `"computer-use-2025-01-24"`3536 - `"pdfs-2024-09-25"`3738 - `"token-counting-2024-11-01"`3940 - `"token-efficient-tools-2025-02-19"`4142 - `"output-128k-2025-02-19"`4344 - `"files-api-2025-04-14"`4546 - `"mcp-client-2025-04-04"`4748 - `"mcp-client-2025-11-20"`4950 - `"dev-full-thinking-2025-05-14"`5152 - `"interleaved-thinking-2025-05-14"`5354 - `"code-execution-2025-05-22"`5556 - `"extended-cache-ttl-2025-04-11"`5758 - `"context-1m-2025-08-07"`5960 - `"context-management-2025-06-27"`6162 - `"model-context-window-exceeded-2025-08-26"`6364 - `"skills-2025-10-02"`6566 - `"fast-mode-2026-02-01"`6768 - `"output-300k-2026-03-24"`6970 - `"user-profiles-2026-03-24"`7172 - `"user-profiles-2026-08-18"`7374 - `"user-profiles-2026-09-04"`7576 - `"advisor-tool-2026-03-01"`7778 - `"managed-agents-2026-04-01"`7980 - `"cache-diagnosis-2026-04-07"`8182 - `"dreaming-2026-04-21"`8384 - `"thinking-token-count-2026-05-13"`8586 - `"server-side-fallback-2026-06-01"`8788 - `"server-side-fallback-2026-07-01"`8990 - `"fallback-credit-2026-06-01"`9192 - `"fallback-credit-2026-07-01"`9394 - `"agent-memory-2026-07-22"`9596 - `"mid-conversation-tool-changes-2026-07-01"`9798 - `"compact-2026-01-12"`99100 - `"computer-use-2025-11-24"`101102 - `"mcp-tunnels-2026-06-22"`103104 - `"structured-outputs-2025-11-13"`105106 - `"task-budgets-2026-03-13"`107108 - `"thinking-display-updates-2026-08-18"`109110 - `"ce-user-management-2026-07-13"`111112 - `"mid-conversation-output-config-2026-07-01"`113114 - `"thinking-binding-controls-2026-08-01"`115116 - `"mid-conversation-system-clear-at-2026-08-21"`117118 - `"compact-2026-09-04"`119120- `"anthropic-workspace-id": optional string`121122## Returns123124- `BetaManagedAgentsSessionThread object`125126 An execution thread within a `session`. Each session has one primary thread plus zero or more child threads spawned by the coordinator.127128 - `type: "session_thread"`129130 - `id: string`131132 Unique identifier for this thread.133134 - `agent: BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`135136 The resolved agent a session thread runs: a saved-agent snapshot, the platform advisor entry, or an inline-defined (ephemeral) agent snapshot.137138 - `BetaManagedAgentsSessionThreadAgent object`139140 Resolved `agent` definition for a single `session_thread`. Snapshot of the agent at thread creation time. The multiagent roster is not repeated here; read it from `Session.agent`.141142 - `type: "agent"`143144 - `id: string`145146 - `description: string or null`147148 - `mcp_servers: array of BetaManagedAgentsMCPServerURLDefinition`149150 - `type: "url"`151152 - `name: string`153154 - `url: string`155156 - `model: BetaManagedAgentsModelConfig`157158 Model identifier and configuration.159160 - `id: BetaManagedAgentsModel`161162 The model that will power your agent.163164 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.165166 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`167168 The model that will power your agent.169170 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.171172 - `"claude-fable-5-1"`173174 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows175176 - `"claude-sonnet-5"`177178 High-performance model for coding and agents179180 - `"claude-fable-5"`181182 Next generation of intelligence for the hardest knowledge work and coding problems183184 - `"claude-opus-5"`185186 Powerful intelligence for long-running agents and coding187188 - `"claude-opus-4-8"`189190 Powerful intelligence for long-running agents and coding191192 - `"claude-opus-4-7"`193194 Powerful intelligence for long-running agents and coding195196 - `"claude-opus-4-6"`197198 Powerful intelligence for long-running agents and coding199200 - `"claude-sonnet-4-6"`201202 Best combination of speed and intelligence203204 - `"claude-haiku-4-5"`205206 Fastest model with near-frontier intelligence207208 - `"claude-haiku-4-5-20251001"`209210 Fastest model with near-frontier intelligence211212 - `"claude-opus-4-5"`213214 Powerful intelligence for long-running agents and coding215216 - `"claude-opus-4-5-20251101"`217218 Powerful intelligence for long-running agents and coding219220 - `"claude-sonnet-4-5"`221222 High-performance model for agents and coding223224 - `"claude-sonnet-4-5-20250929"`225226 High-performance model for agents and coding227228 - `string`229230 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`231232 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.233234 - `BetaManagedAgentsEffortLow object`235236 Low effort. Favors latency over reasoning depth.237238 - `type: "low"`239240 - `BetaManagedAgentsEffortMedium object`241242 Medium effort. Balances latency and reasoning depth.243244 - `type: "medium"`245246 - `BetaManagedAgentsEffortHigh object`247248 High effort. Favors reasoning depth.249250 - `type: "high"`251252 - `BetaManagedAgentsEffortXhigh object`253254 Extra-high effort. Not all models accept this level.255256 - `type: "xhigh"`257258 - `BetaManagedAgentsEffortMax object`259260 Maximum effort. Favors reasoning depth over latency.261262 - `type: "max"`263264 - `inference_geo: optional string`265266 Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.267268 - `speed: optional "standard" or "fast"`269270 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time.271272 - `"standard"`273274 - `"fast"`275276 - `name: string`277278 - `skills: array of BetaManagedAgentsAnthropicSkill or BetaManagedAgentsCustomSkill`279280 - `BetaManagedAgentsAnthropicSkill object`281282 A resolved Anthropic-managed skill.283284 - `type: "anthropic"`285286 - `skill_id: string`287288 - `version: string`289290 - `BetaManagedAgentsCustomSkill object`291292 A resolved user-created custom skill.293294 - `type: "custom"`295296 - `skill_id: string`297298 - `version: string`299300 - `system: string or null`301302 - `tools: array of BetaManagedAgentsAgentToolset20260401 or BetaManagedAgentsMCPToolset or BetaManagedAgentsCustomTool`303304 - `BetaManagedAgentsAgentToolset20260401 object`305306 - `type: "agent_toolset_20260401"`307308 - `configs: array of BetaManagedAgentsAgentToolConfig`309310 - `BetaManagedAgentsBashToolConfig object`311312 Configuration for the bash tool.313314 - `type: "bash"`315316 - `enabled: boolean`317318 - `name: "bash"`319320 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`321322 Permission policy for tool execution.323324 - `BetaManagedAgentsAlwaysAllowPolicy object`325326 Tool calls are automatically approved without user confirmation.327328 - `type: "always_allow"`329330 - `BetaManagedAgentsAlwaysAskPolicy object`331332 Tool calls require user confirmation before execution.333334 - `type: "always_ask"`335336 - `BetaManagedAgentsAutoPolicy object`337338 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.339340 - `type: "auto"`341342 - `BetaManagedAgentsEditToolConfig object`343344 Configuration for the edit tool.345346 - `type: "edit"`347348 - `enabled: boolean`349350 - `name: "edit"`351352 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`353354 Permission policy for tool execution.355356 - `BetaManagedAgentsAlwaysAllowPolicy object`357358 Tool calls are automatically approved without user confirmation.359360 - `BetaManagedAgentsAlwaysAskPolicy object`361362 Tool calls require user confirmation before execution.363364 - `BetaManagedAgentsAutoPolicy object`365366 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.367368 - `BetaManagedAgentsReadToolConfig object`369370 Configuration for the read tool.371372 - `type: "read"`373374 - `enabled: boolean`375376 - `name: "read"`377378 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`379380 Permission policy for tool execution.381382 - `BetaManagedAgentsAlwaysAllowPolicy object`383384 Tool calls are automatically approved without user confirmation.385386 - `BetaManagedAgentsAlwaysAskPolicy object`387388 Tool calls require user confirmation before execution.389390 - `BetaManagedAgentsAutoPolicy object`391392 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.393394 - `BetaManagedAgentsWriteToolConfig object`395396 Configuration for the write tool.397398 - `type: "write"`399400 - `enabled: boolean`401402 - `name: "write"`403404 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`405406 Permission policy for tool execution.407408 - `BetaManagedAgentsAlwaysAllowPolicy object`409410 Tool calls are automatically approved without user confirmation.411412 - `BetaManagedAgentsAlwaysAskPolicy object`413414 Tool calls require user confirmation before execution.415416 - `BetaManagedAgentsAutoPolicy object`417418 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.419420 - `BetaManagedAgentsGlobToolConfig object`421422 Configuration for the glob tool.423424 - `type: "glob"`425426 - `enabled: boolean`427428 - `name: "glob"`429430 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`431432 Permission policy for tool execution.433434 - `BetaManagedAgentsAlwaysAllowPolicy object`435436 Tool calls are automatically approved without user confirmation.437438 - `BetaManagedAgentsAlwaysAskPolicy object`439440 Tool calls require user confirmation before execution.441442 - `BetaManagedAgentsAutoPolicy object`443444 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.445446 - `BetaManagedAgentsGrepToolConfig object`447448 Configuration for the grep tool.449450 - `type: "grep"`451452 - `enabled: boolean`453454 - `name: "grep"`455456 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`457458 Permission policy for tool execution.459460 - `BetaManagedAgentsAlwaysAllowPolicy object`461462 Tool calls are automatically approved without user confirmation.463464 - `BetaManagedAgentsAlwaysAskPolicy object`465466 Tool calls require user confirmation before execution.467468 - `BetaManagedAgentsAutoPolicy object`469470 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.471472 - `BetaManagedAgentsWebFetchToolConfig object`473474 Configuration for the web_fetch tool.475476 - `type: "web_fetch"`477478 - `enabled: boolean`479480 - `name: "web_fetch"`481482 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`483484 Permission policy for tool execution.485486 - `BetaManagedAgentsAlwaysAllowPolicy object`487488 Tool calls are automatically approved without user confirmation.489490 - `BetaManagedAgentsAlwaysAskPolicy object`491492 Tool calls require user confirmation before execution.493494 - `BetaManagedAgentsAutoPolicy object`495496 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.497498 - `allowed_domains: optional array of string`499500 - `blocked_domains: optional array of string`501502 - `max_content_tokens: optional number or null`503504 format: int32505506 - `BetaManagedAgentsWebSearchToolConfig object`507508 Configuration for the web_search tool.509510 - `type: "web_search"`511512 - `enabled: boolean`513514 - `name: "web_search"`515516 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`517518 Permission policy for tool execution.519520 - `BetaManagedAgentsAlwaysAllowPolicy object`521522 Tool calls are automatically approved without user confirmation.523524 - `BetaManagedAgentsAlwaysAskPolicy object`525526 Tool calls require user confirmation before execution.527528 - `BetaManagedAgentsAutoPolicy object`529530 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.531532 - `allowed_domains: optional array of string`533534 - `blocked_domains: optional array of string`535536 - `user_location: optional BetaManagedAgentsUserLocation or null`537538 Approximate user location for search result localization.539540 - `type: "approximate"`541542 Location precision. Only "approximate" is supported.543544 - `city: optional string or null`545546 City name.547548 minLength: 1, maxLength: 255549550 - `country: optional string or null`551552 Two-letter ISO 3166-1 country code, uppercase.553554 - `region: optional string or null`555556 Region or state name.557558 minLength: 1, maxLength: 255559560 - `timezone: optional string or null`561562 IANA timezone identifier, e.g. "America/Los_Angeles".563564 minLength: 1, maxLength: 255565566 - `default_config: BetaManagedAgentsAgentToolsetDefaultConfig`567568 Resolved default configuration for agent tools.569570 - `enabled: boolean`571572 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`573574 Permission policy for tool execution.575576 - `BetaManagedAgentsAlwaysAllowPolicy object`577578 Tool calls are automatically approved without user confirmation.579580 - `BetaManagedAgentsAlwaysAskPolicy object`581582 Tool calls require user confirmation before execution.583584 - `BetaManagedAgentsAutoPolicy object`585586 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.587588 - `BetaManagedAgentsMCPToolset object`589590 - `type: "mcp_toolset"`591592 - `configs: array of BetaManagedAgentsMCPToolConfig`593594 - `enabled: boolean`595596 - `name: string`597598 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`599600 Permission policy for tool execution.601602 - `BetaManagedAgentsAlwaysAllowPolicy object`603604 Tool calls are automatically approved without user confirmation.605606 - `BetaManagedAgentsAlwaysAskPolicy object`607608 Tool calls require user confirmation before execution.609610 - `BetaManagedAgentsAutoPolicy object`611612 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.613614 - `default_config: BetaManagedAgentsMCPToolsetDefaultConfig`615616 Resolved default configuration for all tools from an MCP server.617618 - `enabled: boolean`619620 - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy`621622 Permission policy for tool execution.623624 - `BetaManagedAgentsAlwaysAllowPolicy object`625626 Tool calls are automatically approved without user confirmation.627628 - `BetaManagedAgentsAlwaysAskPolicy object`629630 Tool calls require user confirmation before execution.631632 - `BetaManagedAgentsAutoPolicy object`633634 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.635636 - `mcp_server_name: string`637638 - `BetaManagedAgentsCustomTool object`639640 A custom tool as returned in API responses.641642 - `type: "custom"`643644 - `description: string`645646 - `input_schema: BetaManagedAgentsCustomToolInputSchema`647648 JSON Schema for custom tool input parameters.649650 - `type: "object"`651652 - `properties: optional map[unknown] or null`653654 - `required: optional array of string or null`655656 - `name: string`657658 - `version: number`659660 format: int32661662 - `BetaManagedAgentsAdvisor object`663664 Platform advisor roster entry: a model the session's primary thread may consult mid-turn.665666 - `type: "advisor"`667668 - `model: string`669670 The advisor model id.671672 - `archived_at: string or null`673674 A timestamp in RFC 3339 format675676 format: date-time677678 - `created_at: string`679680 A timestamp in RFC 3339 format681682 format: date-time683684 - `parent_thread_id: string or null`685686 Parent thread that spawned this thread. Null for the primary thread.687688 - `session_id: string`689690 The session this thread belongs to.691692 - `stats: BetaManagedAgentsSessionThreadStats or null`693694 Timing statistics for a session thread.695696 - `active_seconds: optional number`697698 Cumulative time in seconds the thread spent actively running. Excludes idle time.699700 format: double701702 - `duration_seconds: optional number`703704 Elapsed time since thread creation in seconds. For archived threads, frozen at the final update.705706 format: double707708 - `startup_seconds: optional number`709710 Time in seconds for the thread to begin running. Zero for child threads, which start immediately.711712 format: double713714 - `status: BetaManagedAgentsSessionThreadStatus`715716 SessionThreadStatus enum717718 - `"running"`719720 - `"idle"`721722 - `"rescheduling"`723724 - `"terminated"`725726 - `updated_at: string`727728 A timestamp in RFC 3339 format729730 format: date-time731732 - `usage: BetaManagedAgentsSessionThreadUsage or null`733734 Cumulative token usage for a session thread across all turns.735736 - `active_seconds: optional number`737738 Cumulative time in seconds this thread spent in running status. Equal to `stats.active_seconds`; surfaced here so a thread's usage carries every quantity its cost is priced on.739740 format: double741742 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`743744 Prompt-cache creation token usage broken down by cache lifetime.745746 - `ephemeral_1h_input_tokens: optional number`747748 Tokens used to create 1-hour ephemeral cache entries.749750 format: int32751752 - `ephemeral_5m_input_tokens: optional number`753754 Tokens used to create 5-minute ephemeral cache entries.755756 format: int32757758 - `cache_read_input_tokens: optional number`759760 Total tokens read from prompt cache.761762 format: int32763764 - `input_tokens: optional number`765766 Total input tokens consumed across all turns.767768 format: int32769770 - `list_cost: optional BetaMonetaryAmount or null`771772 A monetary amount in a specific currency.773774 - `amount: string`775776 Amount in minor units of the currency, as an integer decimal string with no leading zeros: "2500" is $25.00 and "50" is fifty cents. A string rather than a number so no float rounding is ever applied.777778 - `currency: BetaCurrency`779780 Uppercase ISO-4217 currency code. `USD` is the only currency currently supported; the accepted set is closed and grows only when a new currency is priced.781782 - `output_tokens: optional number`783784 Total output tokens generated across all turns.785786 format: int32787788 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`789790 Cumulative count of server-executed tool invocations, broken down by tool.791792 - `web_fetch_requests: optional number`793794 Number of server-executed web fetch requests.795796 format: int32797798 - `web_search_requests: optional number`799800 Number of server-executed web search requests.801802 format: int32803804## Example805806```bash807curl https://api.anthropic.com/v1/sessions/$SESSION_ID/threads/$THREAD_ID/archive \808 -X POST \809 -H 'anthropic-version: 2023-06-01' \810 -H 'anthropic-beta: managed-agents-2026-04-01' \811 -H "X-Api-Key: $ANTHROPIC_API_KEY"812```813814### Response (200)815816```json817{818 "id": "sthr_011CZkZVWa6oIjw0rgXZpnBt",819 "agent": {820 "id": "agent_011CZkYqphY8vELVzwCUpqiQ",821 "description": "A focused research subagent.",822 "mcp_servers": [823 {824 "name": "example-mcp",825 "type": "url",826 "url": "https://example-server.modelcontextprotocol.io/sse"827 }828 ],829 "model": {830 "id": "claude-opus-5",831 "effort": {832 "type": "low"833 },834 "inference_geo": "inference_geo",835 "speed": "standard"836 },837 "name": "Researcher",838 "skills": [839 {840 "skill_id": "xlsx",841 "type": "anthropic",842 "version": "1"843 }844 ],845 "system": "You are a research subagent that gathers and summarises sources for the coordinating agent.",846 "tools": [847 {848 "configs": [849 {850 "enabled": true,851 "name": "bash",852 "permission_policy": {853 "type": "always_allow"854 },855 "type": "bash"856 }857 ],858 "default_config": {859 "enabled": true,860 "permission_policy": {861 "type": "always_ask"862 }863 },864 "type": "agent_toolset_20260401"865 }866 ],867 "type": "agent",868 "version": 1869 },870 "archived_at": null,871 "created_at": "2026-03-15T10:00:00Z",872 "parent_thread_id": null,873 "session_id": "sesn_011CZkZAtmR3yMPDzynEDxu7",874 "stats": {875 "active_seconds": 0,876 "duration_seconds": 0,877 "startup_seconds": 0878 },879 "status": "idle",880 "type": "session_thread",881 "updated_at": "2026-03-15T10:00:00Z",882 "usage": {883 "active_seconds": 0,884 "cache_creation": {885 "ephemeral_1h_input_tokens": 0,886 "ephemeral_5m_input_tokens": 0887 },888 "cache_read_input_tokens": 0,889 "input_tokens": 0,890 "list_cost": {891 "amount": "2500",892 "currency": "USD"893 },894 "output_tokens": 0,895 "server_tool_use": {896 "web_fetch_requests": 0,897 "web_search_requests": 3898 }899 }900}901```902